Knowledge catalogue
arXiv:2606.23126v1 Announce Type: new Abstract: While recent advancements in anomaly detection have demonstrated the efficacy of CNN- and Transformer-based approaches, these architectures face inheren
arXiv:2606.21119v1 Announce Type: new Abstract: Mammography is an essential tool for breast cancer detection, with millions of examinations conducted annually. However, publicly available high-quality
arXiv:2606.21461v1 Announce Type: new Abstract: The Manipulider is a buoyancy-actuated underwater robot that enables thrusterless, glide-like locomotion and attitude-based manipulation, while providin
arXiv:2606.22597v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to read maps for logistics, delivery, and accessible navigation, where the output is an actionable d
arXiv:2606.22543v1 Announce Type: new Abstract: Humans localize places by integrating perceptual cues from vision with semantic reasoning from language, forming a scene understanding that is both intu
arXiv:2606.22649v1 Announce Type: new Abstract: Foundation models provide highly descriptive representations for medical images, yet their reliability degrades under distribution shifts arising from c
arXiv:2606.23664v1 Announce Type: new Abstract: Multi-agent systems (MAS) offer a scalable path forward for agentic AI, comprising multiple LLM-based agents, each assigned a system prompt and a positi
arXiv:2606.20743v1 Announce Type: new Abstract: Trained transformers reliably develop massive activations, a small number of hidden dimensions whose magnitude is far above the median and which concent
arXiv:2606.21830v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) has driven rapid progress in mathematical and code reasoning, but when extended to science, existi
arXiv:2602.15206v2 Announce Type: replace Abstract: Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, it rem
arXiv:2506.16584v3 Announce Type: replace-cross Abstract: People judge interactions with large language models (LLMs) as successful when outputs match what they want, not what they type. Yet LLMs are
arXiv:2405.09251v2 Announce Type: replace Abstract: Providing various machine learning (ML) applications in the real world, concerns about discrimination hidden in ML models are growing, particularly
arXiv:2511.11625v2 Announce Type: replace Abstract: Artificial intelligence (AI) has shown great potential in medical imaging, particularly for brain tumor detection using Magnetic Resonance Imaging (
arXiv:2606.21194v1 Announce Type: new Abstract: Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains
arXiv:2606.21329v1 Announce Type: new Abstract: Medical time series (MedTS) signals such as electroencephalography (EEG) and electrocardiography (ECG) support many clinical applications. However, subs
arXiv:2606.23455v1 Announce Type: new Abstract: Recent advances integrate physically grounded Newtonian dynamics with neural rendering frameworks, narrowing the gap between photorealistic scene recons
arXiv:2606.21047v1 Announce Type: new Abstract: Acoustic microrobots have emerged as a promising frontier for targeted drug delivery and minimally invasive medicine due to their high-power density and
arXiv:2606.23195v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly rely on memory systems to maintain long-term coherence. Recent work shows that agent memories degrade dur
arXiv:2606.21540v1 Announce Type: new Abstract: Graph convolutional networks (GCNs) have demonstrated significant success in capturing complex user-item relationships for collaborative filtering (CF).
arXiv:2606.20679v1 Announce Type: cross Abstract: Video-world-model policies learn action-relevant representations by predicting future observations. However, they condition on only a short observatio
arXiv:2606.21898v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a promising method for high-quality, real-time 3D reconstruction. To associate 3DGS with mesh representati
arXiv:2606.23489v1 Announce Type: cross Abstract: Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains important
arXiv:2606.22146v1 Announce Type: new Abstract: Meta-reinforcement learning is a promising approach to multi-objective optimisation because it enables rapid policy adaptation across changing environme
arXiv:2512.00324v3 Announce Type: replace-cross Abstract: Imitation learning provides a promising approach to dexterous hand manipulation, but its effectiveness is limited by the lack of large-scale,
arXiv:2601.07298v2 Announce Type: replace Abstract: While Multimodal Large Language Models (MLLMs) excel at single-image understanding, they exhibit significantly degraded performance in multi-image r
arXiv:2606.21344v1 Announce Type: cross Abstract: Trajectory prediction allows autonomous vehicles to anticipate the future behavior of surrounding objects (or agents) and, accordingly, maximize the s
arXiv:2606.20772v1 Announce Type: new Abstract: Camera-first autonomous-driving models predict future ego waypoints from images, ego-state features, and route commands, but waypoint supervision alone
arXiv:2606.23096v1 Announce Type: new Abstract: Minimax risk and regret are expectation-based criteria and do not capture rare but consequential failures. To address this concern, we develop a elta-ex
arXiv:2606.20752v1 Announce Type: new Abstract: Deep neural network-based LiDAR 3D object detection serves as a critical perception component in safety-critical autonomous systems. However, recent stu
arXiv:2606.20717v1 Announce Type: new Abstract: Multimodal Large Language Model (MLLM)-based web agents provide practical, high-precision solutions for visual browser automation; however, they inheren
arXiv:2606.21419v1 Announce Type: new Abstract: Despite recent progress in Vision-Language Models (VLMs), mixed-domain image-caption datasets for both general-purpose and CCTV-based video surveillance
arXiv:2508.13744v2 Announce Type: replace Abstract: Large Vision-Language Models (LVLMs) exhibit strong performance on single-image tasks. However, their performance degrades significantly when handli
arXiv:2606.22551v1 Announce Type: cross Abstract: Hybrid Quantum Neural Network (QNN) classifiers produce logits as expectation values of quantum measurement operators. For standard Pauli measurements
arXiv:2501.03432v3 Announce Type: replace Abstract: The Large Hadron Collider at CERN produces immense volumes of complex data from high-energy particle collisions, demanding sophisticated analytical
arXiv:2603.04035v4 Announce Type: replace Abstract: Dimensionality reduction is a foundational tool for visualizing high-dimensional data, yet its reference implementations span a fragmented stack of
arXiv:2606.22437v1 Announce Type: new Abstract: We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and
arXiv:2606.20906v1 Announce Type: new Abstract: Molecular message-passing neural networks commonly propagate chemically diverse interactions through a single graph, which may mix interaction-specific
arXiv:2603.14145v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong performance in visual and audio understanding when evaluated in isolation. However,
arXiv:2505.12462v3 Announce Type: replace Abstract: Robust reinforcement learning (RL) under the average-reward criterion is essential for long-term decision-making, particularly when the environment
arXiv:2510.25687v3 Announce Type: replace-cross Abstract: Model inversion attacks pose an open challenge to privacy-sensitive applications that use machine learning (ML) models. For example, face auth
arXiv:2602.20208v2 Announce Type: replace Abstract: Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model
arXiv:2606.22702v1 Announce Type: new Abstract: Traditional supervised methods for structured visual recognition tasks -- such as object detection, segmentation, and scene graph generation -- often pr
arXiv:2606.21943v1 Announce Type: new Abstract: Reinforcement learning (RL) has become central to LLM post-training, yet the methods that dominate current pipelines, PPO and GRPO, represent only a nar
arXiv:2606.21033v1 Announce Type: cross Abstract: Image compression for machines calls for a unified codec that serves multiple downstream vision tasks. Existing approaches either adopt task-specific
arXiv:2212.04495v3 Announce Type: replace Abstract: Conventional methods for human motion synthesis are either deterministic or struggle with the trade-off between motion diversity and motion quality.
arXiv:2603.27048v3 Announce Type: replace Abstract: Computational pathology needs whole-slide image (WSI) foundation models that transfer across diverse clinical tasks, yet current approaches remain l
arXiv:2606.23603v1 Announce Type: new Abstract: Unhealthy dietary behavior continues to be a persistent public health issue in the United States, exacerbated by recommendation systems that prioritize
arXiv:2606.22077v1 Announce Type: new Abstract: Morphological traits provide important evidence for phylogenetic reconstruction and evolutionary relationship analysis. Recent image-based approaches ha
arXiv:2606.21764v1 Announce Type: new Abstract: We present MARLNet (Motion-Aware Reinforcement Learning Network), a PPO-based bounding-box refinement agent that incorporates a constant-velocity motion
arXiv:2606.23061v1 Announce Type: new Abstract: Motion instruction generation in cross-video comparison aims to produce corrective feedback that describes the differences between a query and a referen
arXiv:2606.23000v1 Announce Type: new Abstract: Human motion follows a temporal hierarchical structure, transitioning from low-frequency global trajectories to high-frequency details. Inspired by the
arXiv:2606.20705v1 Announce Type: new Abstract: We ask whether the representational hierarchy seen in perception, from local primitives such as edges to higher level structures such as parts and objec
arXiv:2606.21115v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) is a camera-based technique for measuring physiological signals, particularly cardiac activity. From the remotely mea
arXiv:2606.22335v1 Announce Type: new Abstract: Researchers tag and track marine animals to study migration patterns, human impacts on behavior, and behavioral shifts due to climate change. Accurate d
arXiv:2606.22400v1 Announce Type: new Abstract: This study introduces a computationally efficient convolutional neural network (CNN) architecture enhanced with transfer learning for multi-cancer detec
arXiv:2411.19700v5 Announce Type: replace Abstract: Explainable AI methods for vision models aim to identify the parts of the input that are important for the final prediction and subsequently relate
arXiv:2606.22055v1 Announce Type: cross Abstract: Maneuver coordination is a key enabler of connected and automated driving, allowing vehicles to negotiate and execute maneuvers that would otherwise b
arXiv:2502.17583v2 Announce Type: replace-cross Abstract: Multi-year-to-decadal climate predictions are a key tool in understanding the range of potential regional climate futures. Here, we present a
arXiv:2606.22197v1 Announce Type: new Abstract: Dynamic 3D Gaussian splatting faces a fundamental tension between motion consistency and visual fidelity. Deformation-based approaches preserve temporal
arXiv:2606.22377v1 Announce Type: new Abstract: Deep learning has demonstrated significant success for modeling biochemical molecular systems, where inputs are commonly represented as graphs or 3D gri